Generative adversarial networks have been proposed as a way of efficiently training deep generative neural networks. We propose a generative adversarial model that works on continuous sequential data, and apply it by training it on a collection of classical music. We conclude that it generates music that sounds better and better as the model is trained, report statistics on generated music, and let the reader judge the quality by downloading the generated songs.
Constructive Machine Learning Workshop (CML) at NIPS 2016 in Barcelona, Spain, December 10.
Olof Mogren
In this work, we present a discussion forum assistant based on deep recurrent neural networks (RNNs). The assistant is trained to perform three different tasks when faced with a question from a user. Firstly, to recommend related posts. Secondly, to recommend other users that might be able to help. Thirdly, it recommends other channels in the forum where people may discuss related topics. Our recurrent forum assistant is evaluated experimentally by prediction accuracy for the end--to--end trainable parts, as well as by performing an end-user study. We conclude that the model generalizes well, and is helpful for the users.
Representation learning for NLP, RepL4NLP at ACL 2016 in Berlin, August 11.
Jacob Hagstedt P Suorra, Olof Mogren
ACL 2016
First Workshop on Representation Learning for NLP
On November 20th, 2015 at 10:00, I successfully defended my licentiate thesis titled
“Multi-document summarization and semantic relatedness”.
Discussion leader was
Tapani Raiko from Aalto University.
The following students recently wrote their master's theses under my supervision.
Johan Ekdahl and William Axhav Bratt:
CARAI - Development of an intelligent personal assistant for cars
Jacob Hagstedt P Suorra:
Automatic discussion forum assistant using recurrent neural networks
Appeared as a paper in representation learning for NLP, RepL4NLP, at ACL 2016.
Sean Pavlov and Simon Almgren:
Entity recognition in swedish medical documents
Appeared as a paper in the fifth workshop on building and evaluating resources for biomedical text mining (BioTxtM 2016), at COLING 2016.
(Vetenskapsfestivalen)
During the science festival in Gothenburg, we had a session discussing artificial intelligence. The theme for the whole festival was “trust”, so we naturally named our session “Can we trust AI”. I gave an introduction, and shared my view of some of the recent progress that has been made in AI and machine learning, and then we had four other speakers giving their views of current state of the art. Finally, I chaired a discussion session that was much appreciated with the audience. The room was filled, and many people came up to us afterwards and kept the discussion going. The other speakers were Annika Larsson from Autoliv, Ola Gustavsson from Dagens Nyheter, and Hans Salomonsson from Data Intelligence Sweden AB.
(Chalmers Machine Learning Seminars)
Before the representation learning revolution, hand-crafted features were a prerequisite for a successful application of most machine learning algorithms. Just like learned features have been massively successful in many applications, some recent work has shown that you can also automate the learning algorithms themselves. In this talk, I'll cover some of the related ideas presented at this year's NIPS conference.
(FFR135, Artificial Neural Networks)
A motivational talk about deep artificial neural networks, given to the students in FFR135 (Artificial neural networks). I gave motivations for using deep architechtures, and to learn hierarchical representations for data.
(Chalmers Machine Learning Seminars)
Neural models for machine translation was introduced seriously in 2014. With the introduction of attention models their performance improved to levels comparable to those of statistical phrase-based machine translation, the type of translation we are all familiar with through servies like Google Translate.
However, the models have struggled with problems like limited vocabularies, the need of large amounts of data for training, and that they are expensive to train and use.
In the recent months, a number of papers have been published to remedy some of these issues. This includes techniques to battle the limited vocabulary problem, and of using monolingual data to improve the performance. As recently as Monday evening (Sept 26), Google uploaded a paper on their implementation of these ideas, where they claim performance on par with human translators, both counted in BLEU scores, and in human evaluations.
During this talk, I'll go through the ideas behind these recent papers.
(Chalmers Machine Learning Seminars)
An overview over some of the interesting papers presented at ACL this year.
I work as a PhD student in the machine learning research group with problems related to data science and machine learning, using methods from deep learning and graphical models.
I currently teach Algorithms for Machine Learning and Inference. In 2016, I taught a PhD course in Deep Learning, together with Mikael Kågebäck and Fredrik Johansson. I have also taught the AI course (specifically the parts about probabilistic methods, including probabilistic graphical models), Object Oriented Programming, Data Structures, and Algorithms (basic course, and advanced course).
